mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sun 8 Oct 2023

179 papers

  1. Measuring reasoning capabilities of ChatGPTLLM reasoning → Reasoning benchmarks and evaluation
  2. Image Compression and Decompression Framework Based on Latent Diffusion Model for Breast MammographyDiffusion models → Medical imaging and segmentation
  3. How to Teach Programming in the AI Era? Using LLMs as a Teachable Agent for DebuggingLLM agents and tool use → Software engineering coding agents
  4. The Emergence of Reproducibility and Generalizability in Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  5. Explainable Claim Verification via Knowledge-Grounded Reasoning with Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  6. Latent Diffusion Model for Medical Image Standardization and EnhancementDiffusion models → Medical imaging and segmentation
  7. Loose lips sink ships: Mitigating Length Bias in Reinforcement Learning from Human FeedbackLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  8. HOD: A Benchmark Dataset for Harmful Object DetectionLLM safety and security → Safety alignment, refusal and guardrails
  9. Unified speech and gesture synthesis using flow matchingDiffusion models → Audio, speech and music
  10. DeepQTest: Testing Autonomous Driving Systems with Reinforcement Learning and Real-world Weather DataEnd-to-end autonomous driving → Adversarial scenarios and safety testing
  11. Hieros: Hierarchical Imagination on Structured State Space Sequence World ModelsWorld models → Latent dynamics models and model-based RL +1
  12. MenatQA: A New Dataset for Testing the Temporal Comprehension and Reasoning Abilities of Large Language ModelsLLM reasoning → Knowledge- and tool-augmented reasoning
  13. Large Language Model (LLM) as a System of Multiple Expert Agents: An Approach to solve the Abstraction and Reasoning Corpus (ARC) ChallengeLLM reasoning → Multimodal reasoning +1
  14. Transferable Availability Poisoning AttacksLLM safety and security → Backdoor and data poisoning attacks
  15. UReader: Universal OCR-free Visually-situated Language Understanding with Multimodal Large Language ModelMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  16. Bidirectional Knowledge Reconfiguration for Lightweight Point Cloud AnalysisKnowledge distillation → Detection and dense prediction distillation
  17. FedFed: Feature Distillation against Data Heterogeneity in Federated LearningKnowledge distillation → Federated, robust and private distillation
  18. DialCoT Meets PPO: Decomposing and Exploring Reasoning Paths in Smaller Language ModelsLLM reasoning → Prompting and chain-of-thought reasoning
  19. DeVAn: Dense Video Annotation for Video-Language ModelsMultimodal LLMs / vision-language models → Video understanding with MLLMs
  20. BRAINTEASER: Lateral Thinking Puzzles for Large Language ModelsLLM reasoning → Prompting and chain-of-thought reasoning
  21. AvalonBench: Evaluating LLMs Playing the Game of AvalonLLM agents and tool use → Reinforcement learning for LLM agents
  22. Counter Turing Test CT^2: AI-Generated Text Detection is Not as Easy as You May Think -- Introducing AI Detectability IndexLLM reasoning → Reasoning benchmarks and evaluation
  23. Symmetrical Linguistic Feature Distillation with CLIP for Scene Text RecognitionKnowledge distillation → Multimodal distillation
  24. Compositional Semantics for Open Vocabulary Spatio-semantic RepresentationsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  25. Towards Better Chain-of-Thought Prompting Strategies: A SurveyLLM reasoning → Prompting and chain-of-thought reasoning
  26. "A Nova Eletricidade: Aplicacc~oes, Riscos e Tendencias da IA Moderna -- "The New Electricity": Applications, Risks, and Trends in Current AI
  27. Hybrid Quantum-Classical Machine Learning for Sentiment Analysis
  28. Safe Deep Policy Adaptation
  29. Enhancing Document-level Event Argument Extraction with Contextual Clues and Role Relevance
  30. Cross-Task Data Augmentation by Pseudo-label Generation for Region Based Coronary Artery Instance Segmentation
  31. Optimizing Solution-Samplers for Combinatorial Problems: The Landscape of Policy-Gradient Methods
  32. Adversarial Attacks on Combinatorial Multi-Armed Bandits
  33. Successive Data Injection in Conditional Quantum GAN Applied to Time Series Anomaly Detection
  34. Progressive Neural Compression for Adaptive Image Offloading under Timing Constraints
  35. GestSync: Determining who is speaking without a talking head
  36. Tailoring Self-Attention for Graph via Rooted Subtrees
  37. Visual Storytelling with Question-Answer Plans
  38. Hi Guys or Hi Folks? Benchmarking Gender-Neutral Machine Translation with the GeNTE Corpus
  39. MSight: An Edge-Cloud Infrastructure-based Perception System for Connected Automated Vehicles
  40. Clustering Three-Way Data with Outliers
  41. Generalizable Error Modeling for Human Data Annotation: Evidence From an Industry-Scale Search Data Annotation Program
  42. Are Personalized Stochastic Parrots More Dangerous? Evaluating Persona Biases in Dialogue Systems
  43. Enhancing Pre-Trained Language Models with Sentence Position Embeddings for Rhetorical Roles Recognition in Legal Opinions
  44. Physics-tailored machine learning reveals unexpected physics in dusty plasmas
  45. Transforming Pixels into a Masterpiece: AI-Powered Art Restoration using a Novel Distributed Denoising CNN (DDCNN)
  46. Federated Learning: A Cutting-Edge Survey of the Latest Advancements and Applications
  47. Structure-Preserving Instance Segmentation via Skeleton-Aware Distance Transform
  48. A Knowledge Graph-Based Search Engine for Robustly Finding Doctors and Locations in the Healthcare Domain
  49. Persis: A Persian Font Recognition Pipeline Using Convolutional Neural Networks
  50. Simple GNNs with Low Rank Non-parametric Aggregators
  51. In-Context Convergence of Transformers
  52. ChatRadio-Valuer: A Chat Large Language Model for Generalizable Radiology Report Generation Based on Multi-institution and Multi-system Data
  53. SCANet: Scene Complexity Aware Network for Weakly-Supervised Video Moment Retrieval
  54. Enhancing Kernel Flexibility via Learning Asymmetric Locally-Adaptive Kernels
  55. XLS-R fine-tuning on noisy word boundaries for unsupervised speech segmentation into words
  56. MindfulDiary: Harnessing Large Language Model to Support Psychiatric Patients' Journaling
  57. Global Convergence of Policy Gradient Methods in Reinforcement Learning, Games and Control
  58. Physics-aware Machine Learning Revolutionizes Scientific Paradigm for Machine Learning and Process-based Hydrology
  59. Generative Spoken Language Model based on continuous word-sized audio tokens
  60. Accelerating Machine Learning Primitives on Commodity Hardware
  61. Probing Large Language Models from A Human Behavioral Perspective
  62. Semiotics Networks Representing Perceptual Inference
  63. TILFA: A Unified Framework for Text, Image, and Layout Fusion in Argument Mining
  64. Scaling Laws of RoPE-based Extrapolation
  65. ZSC-Eval: An Evaluation Toolkit and Benchmark for Multi-agent Zero-shot Coordination
  66. Boosting Facial Action Unit Detection Through Jointly Learning Facial Landmark Detection and Domain Separation and Reconstruction
  67. GEAR: A GPU-Centric Experience Replay System for Large Reinforcement Learning Models
  68. Towards Optimizing with Large Language Models
  69. A Comparative Study of Voice Conversion Models with Large-Scale Speech and Singing Data: The T13 Systems for the Singing Voice Conversion Challenge 2023
  70. Enhancing Cross-Dataset Performance of Distracted Driving Detection With Score Softmax Classifier And Dynamic Gaussian Smoothing Supervision
  71. GMMFormer: Gaussian-Mixture-Model Based Transformer for Efficient Partially Relevant Video Retrieval
  72. Improving Discriminative Multi-Modal Learning with Large-Scale Pre-Trained Models
  73. LLM-as-a-tutor in EFL Writing Education: Focusing on Evaluation of Student-LLM Interaction
  74. Factuality Challenges in the Era of Large Language Models
  75. Lifelong Learning for Fog Load Balancing: A Transfer Learning Approach
  76. Evolutionary Retrosynthetic Route Planning
  77. Text2NKG: Fine-Grained N-ary Relation Extraction for N-ary relational Knowledge Graph Construction
  78. AANet: Aggregation and Alignment Network with Semi-hard Positive Sample Mining for Hierarchical Place Recognition
  79. DRL-ORA: Distributional Reinforcement Learning with Online Risk Adaption
  80. Optimizing Large Language Models to Expedite the Development of Smart Contracts
  81. Do Large Language Models Know about Facts?
  82. Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity
  83. GSLB: The Graph Structure Learning Benchmark
  84. Multi-Ship Tracking by Robust Similarity metric
  85. Investigating the Ability of PINNs To Solve Burgers' PDE Near Finite-Time BlowUp
  86. Orlicz regrets to consistently bound statistics of random variables with an application to environmental indicators
  87. A Corrected Expected Improvement Acquisition Function Under Noisy Observations
  88. On the Zero-Shot Generalization of Machine-Generated Text Detectors
  89. An Investigation of LLMs' Inefficacy in Understanding Converse Relations
  90. Recurrent Neural Language Models as Probabilistic Finite-state Automata
  91. ITRE: Low-light Image Enhancement Based on Illumination Transmission Ratio Estimation
  92. Toolink: Linking Toolkit Creation and Using through Chain-of-Solving on Open-Source Model
  93. From Data to Dialogue: Leveraging the Structure of Knowledge Graphs for Conversational Exploratory Search
  94. Retrieval-Generation Synergy Augmented Large Language Models
  95. NeuralFastLAS: Fast Logic-Based Learning from Raw Data
  96. ZooPFL: Exploring Black-box Foundation Models for Personalized Federated Learning
  97. Harnessing the Power of Large Language Models for Empathetic Response Generation: Empirical Investigations and Improvements
  98. Maximizing Utilitarian and Egalitarian Welfare of Fractional Hedonic Games on Tree-like Graphs
  99. InstructDET: Diversifying Referring Object Detection with Generalized Instructions
  100. Are Emily and Greg Still More Employable than Lakisha and Jamal? Investigating Algorithmic Hiring Bias in the Era of ChatGPT
All 179
  1. LocoNeRF: A NeRF-based Approach for Local Structure from Motion for Precise Localization
  2. Geometry Aware Field-to-field Transformations for 3D Semantic Segmentation
  3. Fast-DetectGPT: Efficient Zero-Shot Detection of Machine-Generated Text via Conditional Probability Curvature
  4. ed-cec: improving rare word recognition using asr postprocessing based on error detection and context-aware error correction
  5. Instances and Labels: Hierarchy-aware Joint Supervised Contrastive Learning for Hierarchical Multi-Label Text Classification
  6. Cross-domain Robust Deepfake Bias Expansion Network for Face Forgery Detection
  7. Distribution-Based Trajectory Clustering
  8. Dynamic Multi-Domain Knowledge Networks for Chest X-ray Report Generation
  9. Utilizing Contextual Clues and Role Correlations for Enhancing Document-level Event Argument Extraction
  10. Breaking Down Word Semantics from Pre-trained Language Models through Layer-wise Dimension Selection
  11. Lightweight In-Context Tuning for Multimodal Unified Models
  12. Enhancing Representations through Heterogeneous Self-Supervised Learning
  13. OV-PARTS: Towards Open-Vocabulary Part Segmentation
  14. How Graph Neural Networks Learn: Lessons from Training Dynamics
  15. Zero-Shot Detection of Machine-Generated Codes
  16. Intelligent DRL-Based Adaptive Region of Interest for Delay-sensitive Telemedicine Applications
  17. How Reliable Are AI-Generated-Text Detectors? An Assessment Framework Using Evasive Soft Prompts
  18. Asymmetrically Decentralized Federated Learning
  19. Benchmarking Large Language Models with Augmented Instructions for Fine-grained Information Extraction
  20. Learning Generalizable Agents via Saliency-Guided Features Decorrelation
  21. FLatS: Principled Out-of-Distribution Detection with Feature-Based Likelihood Ratio Score
  22. Cross-head mutual Mean-Teaching for semi-supervised medical image segmentation
  23. Revisiting Block-based Quantisation: What is Important for Sub-8-bit LLM Inference?
  24. Towards Scalable Wireless Federated Learning: Challenges and Solutions
  25. Enhancing Argument Structure Extraction with Efficient Leverage of Contextual Information
  26. Unleashing the Multilingual Encoder Potential: Boosting Zero-Shot Performance via Probability Calibration
  27. Robust-GBDT: GBDT with Nonconvex Loss for Tabular Classification in the Presence of Label Noise and Class Imbalance
  28. Guideline Learning for In-context Information Extraction
  29. sign.mt: Real-Time Multilingual Sign Language Translation Application
  30. Pushing the Limits of Pre-training for Time Series Forecasting in the CloudOps Domain
  31. Learning Separable Hidden Unit Contributions for Speaker-Adaptive Lip-Reading
  32. Open-Vocabulary Animal Keypoint Detection with Semantic-feature Matching
  33. FairTune: Optimizing Parameter Efficient Fine Tuning for Fairness in Medical Image Analysis
  34. FP3O: Enabling Proximal Policy Optimization in Multi-Agent Cooperation with Parameter-Sharing Versatility
  35. Accurate battery lifetime prediction across diverse aging conditions with deep learning
  36. Online Learning in Contextual Second-Price Pay-Per-Click Auctions
  37. FakeGPT: Fake News Generation, Explanation and Detection of Large Language Models
  38. Self-Convinced Prompting: Few-Shot Question Answering with Repeated Introspection
  39. Deep Reinforcement Learning Based Cross-Layer Design in Terahertz Mesh Backhaul Networks
  40. Walking Down the Memory Maze: Beyond Context Limit through Interactive Reading
  41. Revisiting Large Language Models as Zero-shot Relation Extractors
  42. Low-Resolution Self-Attention for Semantic Segmentation
  43. Synslator: An Interactive Machine Translation Tool with Online Learning
  44. Single Stage Warped Cloth Learning and Semantic-Contextual Attention Feature Fusion for Virtual TryOn
  45. Fully Spiking Neural Network for Legged Robots
  46. Compressed online Sinkhorn
  47. Human-in-the-loop: The future of Machine Learning in Automated Electron Microscopy
  48. Compresso: Structured Pruning with Collaborative Prompting Learns Compact Large Language Models
  49. Detecting Abnormal Health Conditions in Smart Home Using a Drone
  50. Building an Open-Vocabulary Video CLIP Model with Better Architectures, Optimization and Data
  51. WikiIns: A High-Quality Dataset for Controlled Text Editing by Natural Language Instruction
  52. MinPrompt: Graph-based Minimal Prompt Data Augmentation for Few-shot Question Answering
  53. Self-Knowledge Guided Retrieval Augmentation for Large Language Models
  54. The Reinforce Policy Gradient Algorithm Revisited
  55. SemST: Semantically Consistent Multi-Scale Image Translation via Structure-Texture Alignment
  56. Distantly-Supervised Joint Extraction with Noise-Robust Learning
  57. Prompt-augmented Temporal Point Process for Streaming Event Sequence
  58. VisionFM: a Multi-Modal Multi-Task Vision Foundation Model for Generalist Ophthalmic Artificial Intelligence
  59. Video-Teller: Enhancing Cross-Modal Generation with Fusion and Decoupling
  60. Waveformer for modelling dynamical systems
  61. The Troubling Emergence of Hallucination in Large Language Models -- An Extensive Definition, Quantification, and Prescriptive Remediations
  62. Data-centric Graph Learning: A Survey
  63. A new economic and financial theory of money
  64. Model-adapted Fourier sampling for generative compressed sensing
  65. Comparative Analysis of Transfer Learning in Deep Learning Text-to-Speech Models on a Few-Shot, Low-Resource, Customized Dataset
  66. TopicAdapt- An Inter-Corpora Topics Adaptation Approach
  67. Understanding the Robustness of Multi-modal Contrastive Learning to Distribution Shift
  68. Improved Active Learning via Dependent Leverage Score Sampling
  69. MULTISCRIPT: Multimodal Script Learning for Supporting Open Domain Everyday Tasks
  70. Learning Many-to-Many Mapping for Unpaired Real-World Image Super-resolution and Downscaling
  71. LLM4VV: Developing LLM-Driven Testsuite for Compiler Validation
  72. Exploring the Usage of Chinese Pinyin in Pretraining
  73. Towards Explainable Machine Learning: The Effectiveness of Reservoir Computing in Wireless Receive Processing
  74. Information-Theoretic Bounds on The Removal of Attribute-Specific Bias From Neural Networks
  75. A framework to generate sparsity-inducing regularizers for enhanced low-rank matrix completion
  76. Robust matrix completion via Novel M-estimator Functions
  77. CodeTransOcean: A Comprehensive Multilingual Benchmark for Code Translation
  78. Domain Knowledge Graph Construction Via A Simple Checker
  79. TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting